features.py

import numpy as np
from sklearn.base import BaseEstimator
from HTMLParser import HTMLParser

class FeatureMapper:
    def __init__(self, features):
        self.features = features

    def fit(self, X, y=None):
        for feature_name, column_name, extractor in self.features:
            extractor.fit(X[column_name], y)

    def transform(self, X):
        extracted = []
        for feature_name, column_name, extractor in self.features:
            fea = extractor.transform(X[column_name])
            if hasattr(fea, "toarray"):
                extracted.append(fea.toarray())
            else:
                extracted.append(fea)
        if len(extracted) > 1:
            return np.concatenate(extracted, axis=1)
        else: 
            return extracted[0]

    def fit_transform(self, X, y=None):
        extracted = []
        for feature_name, column_name, extractor in self.features:
            fea = extractor.fit_transform(X[column_name], y)
            if hasattr(fea, "toarray"):
                extracted.append(fea.toarray())
            else:
                extracted.append(fea)
        if len(extracted) > 1:
            return np.concatenate(extracted, axis=1)
        else: 
            return extracted[0]

def identity(x):
    return x

class SimpleTransform(BaseEstimator):
    def __init__(self, transformer=identity):
        self.transformer = transformer

    def fit(self, X, y=None):
        return self

    def fit_transform(self, X, y=None):
        return self.transform(X)

    def transform(self, X, y=None):
        return np.array([self.transformer(x) for x in X], ndmin=2).T